신경회로망을 이용한 원전SG 세관 결함패턴 분류성능 향상기법Performance improvement of Classification of Steam Generator Tube Defects in Nuclear Power Plant Using Neural Network
- Other Titles
- Performance improvement of Classification of Steam Generator Tube Defects in Nuclear Power Plant Using Neural Network
- Authors
- 조남훈; 이향범; 한기원; 송성진
- Issue Date
- Jul-2007
- Publisher
- 대한전기학회
- Keywords
- Eddy Current Testing (ECT); Steam Generator (SG); Neural Network; Pattern Recognition; Feature Extraction; Back-propagation1. 서 론†교신저자; 正會員 : 崇實大 工大 電氣工學部 副敎授工博 E-mail : hyang@ssu.ac.kr*正 會 員 : 崇實大 工大 電氣工學部 助敎授工博; Eddy Current Testing (ECT); Steam Generator (SG); Neural Network; Pattern Recognition; Feature Extraction; Back-propagation1. 서 론†교신저자; 正會員 : 崇實大 工大 電氣工學部 副敎授工博 E-mail : hyang@ssu.ac.kr*正 會 員 : 崇實大 工大 電氣工學部 助敎授工博
- Citation
- 전기학회논문지ABCD, v.56, no.7, pp.1224 - 1230
- Journal Title
- 전기학회논문지ABCD
- Volume
- 56
- Number
- 7
- Start Page
- 1224
- End Page
- 1230
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/18069
- ISSN
- 1229-2443
- Abstract
- - In this paper, we study the classification of defects at steam generator tube in nuclear power plant using eddy current testing(ECT). We consider 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. Through numerical analysis program based on finite element modeling, 400 ECT signals are generated by varying width and depth of each defect type. In order to improve the classification performance, we propose new feature extraction technique. After extracting new features from the generated ECT signals, multi-layer perceptron is used to classify the defect patterns. Through the computer simulation study, it is shown that the proposed method achieves 100% classification success rate while the previous method yields 91% success rate.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.